Giter Club home page Giter Club logo

tss_action_segmentation's Introduction

TSS Action Segmentation

This repository contains code for our AAAI 18 paper: Learning Transferable Subspace for Human Motion Segmentation (TSS). TSS is a novel approach for human action segmentation in time space. It utilizes well labeled source video to improve the target video segmentation performance.

Temporal data clustering is a challenging task. Existing methods usually explore data self-representation strategy, which may hinder the clustering performance in insufficient or corrupted data scenarios. In real-world applications, we are easily accessible to a large number of related labeled data. To this end, we propose a novel transferable subspace clustering approach by exploring useful information from relevant source data to enhance clustering performance in target temporal data. We manage to transform the original data into a shared low-dimensional and distinctive feature space by jointly seeking an effective domain-invariant projection. In this way, the well-labeled source knowledge can help obtain a more discriminative target representation. Moreover, a graph regularizer is designed to incorporate temporal information to preserve more sequence knowledge into the learned representation. Extensive experimental results on 3 human motion datasets demonstrate that our approach can outperform state-of-the-art temporal subspace clustering methods.

Running the code

The code is MATLAB code works in Ubuntu system. Windows system may need minor revision in the folder name. Direct diwnload the code and run TSS_demo.m.

This repository contains two datasets, Weizmann dataset and Keck dataset, which are extracted HOG feature frame by frame. The features are 324-dimension feature metrix.

Authors

Welcome to send us Emails if you have any questions about the code and our work :-)

Papers

This code is corresponding to our AAAI 2018 paper below:

@inproceedings{TSS_Lichen_AAAI18,
	author = {Lichen Wang and Zhengming Ding and Yun Fu},
	title = {Learning Transferable Subspace for Human Motion Segmentation},
	conference = {AAAI Conference on Artificial Intelligence},
	year = {2018},
}

Another extension work with higher performance is accepted by TIP below:

@ARTICLE{Seg_Lichen_TIP18, 
	author={Lichen Wang and Zhengming Ding and Yun Fu}, 
	journal={IEEE Transactions on Image Processing}, 
	title={Low-Rank Transfer Human Motion Segmentation}, 
	year={2019}, 
	volume={28}, 
	number={2}, 
	pages={1023-1034},
	doi={10.1109/TIP.2018.2870945},
}

Please cite our paper if you like or use our work for your research, thank you very much!

tss_action_segmentation's People

Contributors

wanglichenxj avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.